Apple - Mac - verified
Local LLMs that run on MacBook Pro M5 Pro (up to 64 GB)
By this directory's rule of thumb, 33 of 63 open-weight models fit in the 64 GB of unified memory on the MacBook Pro (M5 Pro) in its largest configuration. The largest by total parameters is Qwen3-Coder-Next (79.7B), whose smallest listed download is 44.8 GB, the 4bit MLX build from mlx-community/Qwen3-Coder-Next-4bit.
- Models that fit
- 33 of 63
- Memory
- Up to 64 GB
- Memory type
- Unified memory
- Bandwidth
- 307 GB/s
Spec sheet
- Memory
- Up to 64 GB
- Configurations
- 24, 48 or 64 GB
- Memory type
- Unified memory
- Unified memory
- Yes, shared by CPU and GPU
- Bandwidth
- 307 GB/s
- Released
- 2026
Apple lists 64GB only for M5 Pro with the 20-core GPU, and the memory is shared between CPU and GPU.
Source: Apple spec page (apple.com)
33 models that fit in 64 GB
Total params, largest first| Model | Total params | Smallest download | Quant | Commercial |
|---|---|---|---|---|
| Qwen3-Coder-NextAlibaba Cloud (Qwen) | 79.7B3B active | 44.8 GB | 4bitMLX | Commercial use: Yes |
| NVIDIA Nemotron 3.5 Bolt 74B-A9BNVIDIA | 74.9B9B active | 22.0 GB | 24GB (native 2-bit)GGUF | Commercial use: Yes |
| AI21 Jamba2 MiniAI21 Labs | 51.6B12B active | 31.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.6-35B-A3BAlibaba Cloud (Qwen) | 36B3B active | 20.4 GB | 4bitMLX | Commercial use: Yes |
| Cohere Aya Expanse 32BCohere | 32.3B | 19.8 GB | Q4_K_MGGUF | Commercial use: No |
| Ai2 Olmo 3.1 32B ThinkAi2 | 32.2B | 18.1 GB | 4bitMLX | Commercial use: Yes |
| NVIDIA Nemotron 3.5 Lightning 30B-A3BNVIDIA | 31.6B3B active | 17.8 GB | 4bitMLX | Commercial use: Yes |
| Gemma 4 31BGoogle | 31.3B | 17.7 GB | Q4_0 (QAT)GGUF | Commercial use: Yes |
| IBM Granite 4.2 30BIBM | 29.3B | 16.5 GB | 4bitMLX | Commercial use: Yes |
| Qwen3.8-27BAlibaba Cloud (Qwen) | 27.8B | 16.1 GB | 4bitMLX | Commercial use: Yes |
| Gemma 4 26B A4BGoogle | 25.8B3.8B active | 14.4 GB | Q4_0 (QAT)GGUF | Commercial use: Yes |
| Devstral Small 2 24B Instruct 2512Mistral AI | 24B | 14.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Liquid AI LFM2.5-24B-A2BLiquid AI | 24B2.5B active | 13.6 GB | 4bitMLX | Commercial use: Conditions |
| gpt-oss-20bOpenAI | 20.9B3.6B active | 11.2 GB | MXFP4-Q4MLX | Commercial use: Yes |
| Phi-4-reasoning-vision-15BMicrosoft | 15.1B | 30.2 GB | BF16Official weights | Commercial use: Yes |
| Phi-4Microsoft | 14.7B | 8.2 GB | 4bitMLX | Commercial use: Yes |
| Phi-4-reasoning-plusMicrosoft | 14.7B | 9.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 14B Instruct 2512Mistral AI | 13.9B | 8.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| Gemma 4 12BGoogle | 12B | 6.7 GB | 4bitMLX | Commercial use: Yes |
| Qwen3.5-9BAlibaba Cloud (Qwen) | 9.7B | 5.7 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 8B Instruct 2512Mistral AI | 8.9B | 5.2 GB | Q4_K_MGGUF | Commercial use: Yes |
| IBM Granite 4.2 8BIBM | 8.8B | 4.9 GB | 4bitMLX | Commercial use: Yes |
| Cohere Command R7B (12-2024)Cohere | 8B | 4.5 GB | 4bitMLX | Commercial use: No |
| Gemma 4 E4BGoogle | 8B | 5.0 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ai2 Olmo Hybrid Instruct DPO 7BAi2 | 7.4B | 14.9 GB | BF16Official weights | Commercial use: Yes |
| Gemma 4 E2BGoogle | 5.1B | 3.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.5-4BAlibaba Cloud (Qwen) | 4.7B | 2.7 GB | Q4_K_MGGUF | Commercial use: Yes |
| Ministral 3 3B Instruct 2512Mistral AI | 3.8B | 2.1 GB | Q4_K_MGGUF | Commercial use: Yes |
| Phi-4-mini-instructMicrosoft | 3.8B | 2.2 GB | 4bitMLX | Commercial use: Yes |
| Phi-4-mini-reasoningMicrosoft | 3.8B | 2.2 GB | 4bitMLX | Commercial use: Yes |
| Liquid AI LFM2.5-2.6BLiquid AI | 2.7B | 1.6 GB | 4bitMLX | Commercial use: Conditions |
| Qwen3.5-2BAlibaba Cloud (Qwen) | 2.3B | 1.3 GB | Q4_K_MGGUF | Commercial use: Yes |
| Qwen3.5-0.8BAlibaba Cloud (Qwen) | 0.9B | 0.5 GB | Q4_K_MGGUF | Commercial use: Yes |
The rest of the 63 need more than 64 GB. Browse every local model.
By memory configuration
Apple sells the MacBook Pro (M5 Pro) with 24, 48 or 64 GB. The same rule applied to each configuration, and the models each step up adds.
| Configuration | Models that fit | Largest that fits | New at this size |
|---|---|---|---|
| 24 GB | 28 / 63 | Cohere Aya Expanse 32B | Base configuration: 28 models |
| 48 GB | 32 / 63 | NVIDIA Nemotron 3.5 Bolt 74B-A9B | NVIDIA Nemotron 3.5 Bolt 74B-A9B, AI21 Jamba2 Mini, Qwen3.6-35B-A3B, Phi-4-reasoning-vision-15B |
| 64 GB | 33 / 63 | Qwen3-Coder-Next | Qwen3-Coder-Next |
Other devices with 64 GB
Same memory size. Each shows how many models fit under its own rule (Macs also count MLX builds), and the memory type and bandwidth differ.
Compare all 33 GPUs and Macs by memory, bandwidth and how many models fit.
FAQ
How many local LLMs can the MacBook Pro (M5 Pro) run?
33 of the 63 open-weight models in this directory fit in its largest configuration, 64 GB, by this site's rule of thumb that the smallest listed download is at most 85% of the memory. By configuration: 28 at 24 GB, 32 at 48 GB and 33 at 64 GB.
Can the MacBook Pro (M5 Pro) run Qwen3-Coder-Next?
Yes, by this directory's rule of thumb: its smallest listed download, 44.8 GB, is at most 85% of 64 GB (54.4 GB), the 4bit MLX build from mlx-community/Qwen3-Coder-Next-4bit. That leaves room for the context and the operating system. It is a memory check, not a speed estimate.
Can the MacBook Pro (M5 Pro) run NVIDIA Nemotron 3.5 Bolt 74B-A9B?
Yes, by this directory's rule of thumb: its smallest listed download, 22.0 GB, is at most 85% of 64 GB (54.4 GB), the 24GB (native 2-bit) GGUF build from nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-GGUF. That leaves room for the context and the operating system. It is a memory check, not a speed estimate.
Can the MacBook Pro (M5 Pro) run GLM-4.5-Air?
Not by this directory's rule of thumb: its smallest listed download, 60.1 GB, is more than 85% of 64 GB (54.4 GB). It needs the 128 GB tier or more: https://www.developersdigest.tech/local-models/fits/128.
Is the MacBook Pro (M5 Pro)'s memory shared with the operating system?
Yes. Apple lists unified memory shared by the CPU and GPU, so the operating system and your apps use the same pool as the model. The 15% headroom in this directory's rule is there for that and for the context.
What memory bandwidth does the MacBook Pro (M5 Pro) have?
Apple states 307 GB/s of memory bandwidth (Unified memory). From the spec notes: Apple lists 64GB only for M5 Pro with the 20-core GPU, and the memory is shared between CPU and GPU. This page does not turn bandwidth into a speed estimate.
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.